Attention! This forum will be made read-only by Dec-20. Please migrate to https://forum.opencv.org. Most of existing active users should've received invitation by e-mail.
Ask Your Question

crackwitz's profile - activity

2020-12-03 16:31:28 -0500 answered a question How to discover the input and output format of a cv::dnn::Net?

the network's description can tell you the dimensions of every layer, particularly first and last layers. it can't tell

2020-12-03 16:27:21 -0500 commented answer Training for roof tile detection

those response peaks are the result of matchTemplate or other correlation methods. they indicate the strength of the cor

2020-12-03 16:26:11 -0500 commented answer Training for roof tile detection

those are the result of matchTemplate or other correlation methods. they indicate the strength of the correlation for th

2020-12-03 11:44:56 -0500 commented question Why is the processImage delegate not getting called automatically?

the documentation for the Objective C bindings are very bare. unfortunately you are in uncharted territory. maybe this t

2020-12-03 11:44:37 -0500 commented question Why is the processImage delegate not getting called automatically?

the documentation for the Objective C bindings are very bare. unfortunately you are in uncharted territory. maybe this t

2020-12-03 11:44:09 -0500 commented question Why is the processImage delegate not getting called automatically?

the documentation for the Objective C bindings are very bare. unfortunately you are in uncharted territory. maybe this t

2020-12-03 11:42:24 -0500 commented question Why is the processImage delegate not getting called automatically?

the documentation for the Objective C bindings are very bare. unfortunately you are in uncharted territory. https://docs

2020-12-03 11:36:09 -0500 answered a question Training for roof tile detection

here's how I would solve it: ask the user to click on the corners of a rectangle on the roof warp the picture so

2020-12-03 11:13:40 -0500 commented question historical performance test cast data in build pipeline?

I doubt it. performance depends on the machine the test is run on. you'd need a reference machine to make values compara

2020-12-03 11:11:26 -0500 answered a question Convert a Video.mp4 in a 2D Matrix where each row represents a frame

numpy stacking creates a copy because it's impossible to enlarge arrays in-place. thus, you are copying the whole array

2020-12-02 14:26:15 -0500 commented question How can I track the disappearance of a TV logo in a certain area in a frame (ROI)?

what approaches have you tried so far?

2020-12-02 14:25:34 -0500 commented question How can I track the disappearance of a TV logo in a certain area in a frame (ROI)?

please provide some pictures

2020-12-02 14:24:31 -0500 commented question imshow no window on Mac Big Sur with Python

you are going to need to contact the maintainer of that python package, skvarg. he will need to figure out what's going

2020-12-02 14:19:28 -0500 commented answer Finding center of contour in a game

here are some keywords: cv::inRange, morphological operations (closing in particular), cv::findContours, connected compo

2020-12-02 14:18:52 -0500 commented answer Finding center of contour in a game

here are some keywords: cv::inRange, morphological operations (closing in particular), cv::findContours, connected compo

2020-12-02 14:16:24 -0500 commented question Duplicate frames in saved file from cv2.VideoWriter

post your code, or the pieces that could be relevant. the VideoWriter is likely not at fault, but something else is goin

2020-12-02 14:15:53 -0500 commented question Duplicate frames in saved file from cv2.VideoWriter

setting CAP_PROP_FPS on a VideoWriter object is purely metadata. the VideoWriter always writes as fast as possible, whic

2020-12-02 14:14:48 -0500 commented question Duplicate frames in saved file from cv2.VideoWriter

post your code, or the pieces that could be relevant. the VideoWriter is likely not at fault, but something else is goin

2020-12-02 14:12:33 -0500 commented question stitch transform reuse

precisely, the link doesn't apply to the situation

2020-12-02 01:25:04 -0500 commented question Converting image to grayscale

post all relevant code. speculate on what the error message could mean (read it).

2020-12-01 21:10:16 -0500 commented question stitch transform reuse

that's for 5 images/videos, not 5-channel data

2020-12-01 21:09:03 -0500 commented answer stitch transform reuse

OpenCV comes with simple and detailed stitching sample source and accompanying, very brief, "tutorial" article https://d

2020-12-01 11:25:19 -0500 edited answer stitch transform reuse

I took a quick peek at the stitcher API it recommends that you familiarize yourself with its pipeline it appears that

2020-12-01 11:25:07 -0500 edited answer stitch transform reuse

I took a quick peek at the stitcher API it recommends that you familiarize yourself with its pipeline it appears that

2020-12-01 11:23:37 -0500 edited answer stitch transform reuse

I took a quick peek at the stitcher API it recommends that you familiarize yourself with its pipeline it appears that

2020-12-01 11:22:07 -0500 answered a question stitch transform reuse

I took a quick peek at the stitcher API it appears that you can run estimateTransform() separately from composePanorama

2020-12-01 11:06:35 -0500 answered a question Birdseye transform with getPerspectiveTransform

your code doesn't contain getPerspectiveTransform. do you have the homography matrix returned by that call? the homogra

2020-12-01 10:56:59 -0500 commented answer PatMax in OpenCV

for a "Bag of Visual Words" approach, maybe check this out https://agmanic.com/image-classification-with-bag-of-visual-w

2020-12-01 10:53:33 -0500 commented answer PatMax in OpenCV

I'm not sure what geometric matching entails. the closest I can imagine those things to work is by feature matching and

2020-11-30 11:22:22 -0500 answered a question PatMax in OpenCV

there may be free/open libraries that rival the commercial optical inspection libraries but I don't know any. OpenCV ha

2020-11-28 15:22:09 -0500 answered a question Opencv and OAK on Mac with new chip M1

the Apple M1 chip is based on ARM. OpenCV builds fine for ARM. The Raspberry Pi is an ARM processor and many people use

2020-11-28 15:12:41 -0500 commented answer Face detection and time - video

comparing numbers with the "is" operator is not recommended. the "is" operator tests identity, which is useful for objec

2020-11-28 15:03:22 -0500 edited answer Face detection and time - video

the video plays faster than realtime because that's a useful behavior to rapidly work through data. if you want it to "

2020-11-28 15:00:08 -0500 answered a question Face detection and time - video

the video plays faster than realtime because that's a useful behavior to rapidly work through data. if you want it to "

2020-11-27 21:23:44 -0500 commented question How to check if camera is enabled?

what do you mean, "enabled"? OpenCV can't know if any video device in your system is currently being used. that's not Op

2020-11-27 21:20:34 -0500 commented answer Reduce frame resolution

or you could instead request a lower resolution picture from the system (android API)...

2020-11-27 21:19:25 -0500 commented answer Reduce frame resolution

yes image resizing exists in 2.4. you could check the docs for v2.4 if you are unsure. they are still on the web.

2020-11-27 13:01:00 -0500 commented answer Reduce frame resolution

tips: use INTER_AREA for good results of severe downsampling. pyrDown(), is also an easy option.

2020-11-27 12:57:35 -0500 commented question guidance for mapping 2D image onto 3D geometry

a point cloud isn't a surface. you'll have to process your point cloud into a mesh surface or other surface description

2020-11-27 12:56:28 -0500 commented question guidance for mapping 2D image onto 3D geometry

also, DO NOT use "tutroals". it's out of date by five years and all of that content is in docs.opencv.org anyway.

2020-11-27 12:55:49 -0500 commented question guidance for mapping 2D image onto 3D geometry

a point cloud isn't a surface. you'll have to process your point cloud into a mesh surface or other surface description

2020-11-26 10:13:18 -0500 received badge  Organizer (source)
2020-11-26 10:08:09 -0500 commented answer Trying to use MultiBandBlender in Java

please feel encouraged to open an issue on github, requesting java bindings for the module (or the parts you need at lea

2020-11-26 10:03:34 -0500 commented question How to know the exact location of an object in an image after detecting it using haar-cascade?

congratulations on training a haar cascade classifier. now run cv::CascadeClassifier::detectMultiScale()

2020-11-25 20:14:10 -0500 edited answer Tracking a large number of dots on a cloth

I'm unaware of anything in OpenCV that is a complete solution to this. I hope you'll get answers that come closer to a s

2020-11-25 20:04:58 -0500 edited answer Tracking a large number of dots on a cloth

I'm unaware of anything in OpenCV that is a complete solution to this. I hope you'll get answers that come closer to a s

2020-11-25 19:59:13 -0500 edited answer Tracking a large number of dots on a cloth

I'm unaware of anything in OpenCV that is a complete solution to this. I hope you'll get answers that come closer to a s

2020-11-25 19:58:48 -0500 edited answer Tracking a large number of dots on a cloth

I'm unaware of anything in OpenCV that is a complete solution to this. I hope you'll get answers that come closer to a s

2020-11-25 19:57:58 -0500 edited answer Tracking a large number of dots on a cloth

I'm unaware of anything in OpenCV that is a complete solution to this. I hope you'll get answers that come closer to a s

2020-11-25 19:50:21 -0500 edited answer Tracking a large number of dots on a cloth

I'm unaware of anything in OpenCV that is a complete solution to this. I hope you'll get answers that come closer to a s